Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/synaptiai/synapti-marketplaceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/synaptiai/synapti-marketplace/gh-setup)<a href="https://agentmods.dev/commands/synaptiai/synapti-marketplace/gh-setup"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/gh-setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/synaptiai/synapti-marketplace/gh-setup"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/gh-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.06556 |
| Opus 5 | $0.00015 | $0.03278 |
| Sonnet 5 | $0.00006 | $0.01311 |
| Haiku 4.5 | $0.00003 | $0.00656 |
Grade B, and why
gh-setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep '<!-- gh-workflow:' .claude/CLAUDE.md 2>/dev/null || echo "No version marker found" How it starts
The opening of the file, as written. The whole thing — 709 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup / Update GitHub Workflow
Analyze the current repository and generate customized GitHub workflow configuration. If gh-workflow is already configured, detect the existing version and offer to update it with new commands and features while preserving customizations.
Tool Usage: This workflow uses the AskUserQuestion tool extensively to gather preferences, confirm detected conventions, and approve generated configurations.
Contract
GOAL: Project-specific workflow configuration generated, applied, or updated based on detected tech stack and conventions. Testable: .claude/CLAUDE.md contains workflow section with correct branch/commit conventions, all current gh-workflow commands listed, and version marker reflecting current plugin version ($PLUGIN_VERSION from plugin.json).
CONSTRAINTS:
- Never overwrite existing CLAUDE.md - merge or append the workflow section
- Always create backup before modifying existing files
- Always confirm detected patterns with user before applying
FORMAT: Generated CLAUDE.md workflow section with branching strategy, commit conventions, commands table, and tech-stack-specific quality checklist.
FAILURE CONDITIONS (output is unacceptable if any apply):
- Existing CLAUDE.md overwritten without backup
- Wrong tech stack detected (e.g., Python project identified as Go)
- Configuration applied without user preview and approval
- Generated conventions conflict with existing project conventions
- Existing customizations lost during update (branch naming, labels, checklists)
Purpose
This command analyzes your codebase and generates:
- A
.claude/CLAUDE.mdsection with GitHub workflow documentation - Optionally, local command overrides for project-specific customizations
- Recommendations for labels to create
Phase 0: Installation Detection
Before performing any analysis, read the plugin version and detect whether gh-workflow is already configured.
- Read plugin version (single source of truth):
# Try known plugin locations (marketplace source, then cache, then local dev) PLUGIN_VERSION="" # Marketplace source (unversioned, always matches installed version) for MARKET in "$HOME/.claude/plugins/marketplaces"/*/plugins/gh-workflow/.claude-plugin/plugin.json; do [ -f "$MARKET" ] && { PLUGIN_VERSION=$(jq -r '.version' "$MARKET"); break; } done # Cache (versioned dirs — take the latest) if [ -z "$PLUGIN_VERSION" ]; then LATEST=$(ls -d "$HOME/.claude/plugins/cache"/*/gh-workflow/*/.claude-plugin/plugin.json 2>/dev/null | sort -V | tail -1) [ -n "$LATEST" ] && PLUGIN_VERSION=$(jq -r '.version' "$LATEST") fi # Local development (running from marketplace repo) [ -z "$PLUGIN_VERSION" ] && [ -f "plugins/gh-workflow/.claude-plugin/plugin.json" ] && \ PLUGIN_VERSION=$(jq -r '.version' "plugins/gh-workflow/.claude-plugin/plugin.json") [ -z "$PLUGIN_VERSION" ] && PLUGIN_VERSION="unknown" echo "gh-workflow version: $PLUGIN_VERSION"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 709 lines · 31 tokens per session scan B 893f52d35caa
gh-setup is a command published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 6,556 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-10.
Other commands, from other repositories
create-worktree
Follow these steps to create a git worktree.
ship
Ship workflow — detect base branch, merge, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR.
document-release
Post-ship documentation update — reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped.
deploy
Start Phase 6 — propose a deployment for human approval and, once approved, execute with post-deploy verification.
resolve-review
Resolve reviewer feedback - from GitHub PRs, chat, or any reviewer.
release
Release the plugin — bump version across 4 files, then optionally commit, tag, push, and create a GitHub Release.